Vanilla Policy Optimization Is Both Optimal and Differentially Private for Stochastic Contextual Bandits

arXiv:2609.33888 · cs.LG · Submitted 2026-09-27 · Read on arXiv

cs.LG

Submitted: 2026-09-27

Updated: 2026-09-27

Code: https://github.com/alex-rbch/private-contextual-bandits

Terminology

• Contextual Bandits — 1× in this paper · explained in 3 episodes
• Differentially Private — 1× in this paper · explained in 3 episodes

Sources

• Making Contextual Decisions with Low Technical Debt
• Beyond Covariance Matrix: The Statistical Complexity of Private Linear Regression
• Towards Differentially Private Reinforcement Learning with General Function Approximation
• Optimal Regret for Policy Optimization in Contextual Bandits
• Shuffle and Joint Differential Privacy for Generalized Linear Contextual Bandits
• Proximal Policy Optimization Algorithms
• Upper Counterfactual Confidence Bounds: a New Optimism Principle for Contextual Bandits

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks